© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9577
    Prev
    Next
    INDEX
    Explanations

    zip code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģå±Ĥ
    -0.10
    éĻIJæŶ
    -0.09
     sink
    -0.09
    èĤīä½ĵ
    -0.09
    æ²¹çĶ°
    -0.08
     Sham
    -0.08
    ä¸Ģæ³¢
    -0.08
    ä¸įäºĨ
    -0.08
    ĪæĿĥ
    -0.08
    ä¸Ģéģĵ
    -0.08
    POSITIVE LOGITS
     ÑģÑĤоÑĢон
    0.09
    赤
    0.09
    æī«ä¸Ģæī«
    0.09
    è£ħå¤ĩåĪ¶éĢł
    0.09
    èįª
    0.09
    å²Ĺä½į
    0.09
     Joh
    0.09
    flix
    0.08
    éĢĤåIJĪèĩªå·±
    0.08
    å´ĩé«ĺ
    0.08
    Activations Density 0.003%

    No Known Activations